ConPro: Contrast Projection Pretraining for Label-Efficient Vessel Segmentation in DSA Sequences

Paper recorded by Signals 4 on 2026-09-24 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-24 on arXiv · recorded by Signals 4 on 2026-09-25

Category: cs.CV · 计算机视觉 · first seen 2026-09-25

Abstract

Dense vessel annotation in digital subtraction angiography (DSA) is labor-intensive, yet every unlabeled sequence records how contrast passes through the vessels. Semi-supervised methods take their targets from the current model, and generic self-supervised pretexts reconstruct static appearance, so this signal goes unused. We propose ConPro, a self-supervised pretraining scheme whose target is a

Read on arXiv →